A Survey of Data Augmentation in Domain Generalization
Neural Processing Letters · 22.03.2025 · 57 (2)
DOI: 10.1007/s11063-025-11747-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Processing Letters, online erschienen am 22.03.2025. Verfasst von Yingyi Zhong und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 205 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Most machine learning algorithms typically assume that the data distribution of the training and test sets are consistent, but this assumption often fails to hold in practical applications. Domain generalization aims to train a model using only available source data so that the model can generalize to unseen domains. Data augmentation is an important technique in domain generalization, but there are few comprehensive reviews investigating and summarizing its use in domain generalization. This study provides a comprehensive literature review of data augmentation methods in domain generalization for the first time. First, we formalize the definition of domain generalization and analyze the role of data augmentation in domain generalization. Second, we propose a new taxonomy that categorizes methods into three classes based on the augmentation objectives: domain-level, image-level, and feature-level augmentation. Third, we compare the experimental results of some data augmentation methods on three popular domain generalization datasets and discuss the characteristics and advantages of the current best methods. Fourth, we analyze the shortcomings of each category, propose the suggestions for improvements, and summarize the challenges and the future directions of data augmentation for achieving cross-domain generalization from both theoretical and practical perspectives.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhong, Y., Zhou, W., & Wang, Z. (2025). A Survey of Data Augmentation in Domain Generalization. Neural Processing Letters, 57(2). https://doi.org/10.1007/s11063-025-11747-9
Vancouver
Zhong Y, Zhou W, Wang Z. A Survey of Data Augmentation in Domain Generalization. Neural Processing Letters. 2025;57(2). doi:10.1007/s11063-025-11747-9
BibTeX
@article{Zhong2025,
author = {Zhong, Yingyi and Zhou, Wen’an and Wang, Zhixian},
title = {A Survey of Data Augmentation in Domain Generalization},
journal = {Neural Processing Letters},
year = {2025},
volume = {57},
number = {2},
doi = {10.1007/s11063-025-11747-9}
}
EUVIMED